Summary of Feature Inference Attack on Shapley Values, by Xinjian Luo et al.
Feature Inference Attack on Shapley Values
by Xinjian Luo, Yangfan Jiang, Xiaokui Xiao
First submitted to arxiv on: 16 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper discusses the Shapley value concept in cooperative game theory as a solution for model interpretability in Machine Learning as a Service (MLaaS). The Shapley value has been widely adopted by leading MLaaS providers like Google, Microsoft, and IBM. However, researchers have neglected to consider the privacy risks associated with using Shapley values despite their importance in machine learning models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper highlights the importance of considering both model interpretability and privacy when developing machine learning models. It notes that while the Shapley value has been widely used for model interpretability, it may also pose privacy risks. The paper aims to bridge this gap by exploring the intersection of model interpretability and privacy. |
Keywords
» Artificial intelligence » Machine learning
